Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    examples or instances of different concepts or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that signify examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.85
    ulum
    -0.74
    lene
    -0.74
    ossier
    -0.69
    earchers
    -0.69
    houses
    -0.68
    cles
    -0.67
    culosis
    -0.67
    hya
    -0.66
     Tours
    -0.66
    POSITIVE LOGITS
     collateral
    0.89
     unintended
    0.84
     heroism
    0.83
     how
    0.76
     plagiar
    0.76
     constructive
    0.75
     blatant
    0.73
     hypocrisy
    0.72
     spontaneous
    0.71
     divergence
    0.71
    Act Density 0.116%

    No Known Activations